Clinical Benchmarks

Xiaomi

Xiaomi models with results here, each placed on its own board.

Models
4
Results
9
Boards
3 of 13

mimo.xiaomi.com

Models

ModelKindReleasedBoards
MiMo V2.6 FlashModel22 Sep 20262
MiMo V2.6 ProModel22 Sep 20262
MiMo V2.5ModelNot stated2
MiMo V2.5 ProModelNot stated3

Results

One line per result. Dark tick: the board leader.

Documentation and coding

  1. MedScribe (Vals AI)
    model ID xiaomi/mimo-v2.6-pro; temperature=1; top_p=0.95; max_output_tokens=128000
    88.31
    Rank 11 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  2. MedScribe (Vals AI)
    model ID xiaomi/mimo-v2.6-flash; temperature=1; top_p=0.95; max_output_tokens=128000
    85.28
    Rank 27 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  3. MedScribe (Vals AI)
    model ID xiaomi/mimo-v2.5-pro; temperature=1; top_p=0.95; max_output_tokens=30000
    83.73
    Rank 39 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  4. MedScribe (Vals AI)
    model ID xiaomi/mimo-v2.5; temperature=1; top_p=0.95; max_output_tokens=30000
    72.15
    Rank 86 of 105Leader Claude Opus 5.5 91.43
    Official leaderboard
    Measured Sep 2026
  5. MedCode (Vals AI)
    model ID xiaomi/mimo-v2.6-pro; temperature=1; top_p=0.95; max_output_tokens=128000
    44.97
    Rank 36 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  6. MedCode (Vals AI)
    model ID xiaomi/mimo-v2.6-flash; temperature=1; top_p=0.95; max_output_tokens=128000
    41.06
    Rank 55 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  7. MedCode (Vals AI)
    model ID xiaomi/mimo-v2.5-pro; temperature=1; top_p=0.95; max_output_tokens=30000
    32.48
    Rank 85 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026
  8. MedCode (Vals AI)
    model ID xiaomi/mimo-v2.5; temperature=1; top_p=0.95; max_output_tokens=30000
    31.89
    Rank 88 of 103Leader Claude Opus 5 63.57
    Official leaderboard
    Measured Sep 2026

EHR and workflow agents

  1. PhysicianBench
    Pass@1 over 3 runs; Pass^3 6.0; shared FHIR tool harness; up to 100 turns; high reasoning when supported
    16.7
    Rank 17 of 21 here, 12 models on the boardLeader Claude Opus 5.5 (max) 68.4
    Official leaderboard
    Measured May 2026